Prepare

library(tidyverse, warn.conflicts = F)

## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr     1.1.4     ✔ readr     2.1.4
## ✔ forcats   1.0.0     ✔ stringr   1.5.1
## ✔ ggplot2   3.4.4     ✔ tibble    3.2.1
## ✔ lubridate 1.9.3     ✔ tidyr     1.3.0
## ✔ purrr     1.0.2     
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors

library(plotly)

## 
## Attaching package: 'plotly'
## 
## The following object is masked from 'package:ggplot2':
## 
##     last_plot
## 
## The following object is masked from 'package:stats':
## 
##     filter
## 
## The following object is masked from 'package:graphics':
## 
##     layout

library(ggplot2)
library(purrr) # for functional programming
df <- read.csv("data/netflix_titles.csv", na.strings = c("", "NA"))

Get country information

grouped <- df %>%
  filter(!is.na(country) & country != "") %>%
  mutate(country = strsplit(as.character(country), ",")) %>%
  mutate(country = lapply(country, trimws)) %>%
  unnest(country) %>%
  group_by(country, release_year, type) %>%
  summarise(cnt = n()) %>%
  filter(!is.na(country) & country != "")

## `summarise()` has grouped output by 'country', 'release_year'. You can override
## using the `.groups` argument.

Grouping

by_country_type <- grouped %>% group_by(country, type) %>%
  summarise(cnt = sum(cnt))

## `summarise()` has grouped output by 'country'. You can override using the
## `.groups` argument.

Movie Distribution by country

plot_ly(by_country_type %>% filter(type == "Movie"), 
               type = 'choropleth',
               locations = ~country,
               locationmode = 'country names',
               z = ~cnt,
               color = ~cnt,
               colors = 'OrRd',
               colorbar = list(title = 'Counts'),
               text = ~paste(country, "<br>Counts: ", cnt)
)

TV Show Distribution by contry

plot_ly(by_country_type %>% filter(type == "TV Show"), 
               type = 'choropleth',
               locations = ~country,
               locationmode = 'country names',
               z = ~cnt,
               color = ~cnt,
               colors = 'OrRd',
               colorbar = list(title = 'Counts'),
               text = ~paste(country, "<br>Counts: ", cnt)
)